Industrial situation awareness multi-sensor fusion data collaborative analysis method and system

Abstract

The invention provides an industrial situation awareness multi-sensor fusion data collaborative analysis method and system, and relates to the technical field of industrial sensors, and the method specifically comprises the steps: collecting sensor data, analyzing the correlation between sensors, longitudinally analyzing the data, and outputting a judgment result. According to the invention, correlation analysis is carried out on data collected by sensors on equipment, the sensors work together and cooperatively, the correlation between the sensors is analyzed by collecting the data of the sensors, and longitudinal analysis is carried out on the data collected by the sensors at the same sampling points and collection windows on the basis of the correlation; and a fault category judgment index for judging a fault occurrence source is generated, so that whether the equipment has a fault or the sensor has a fault is judged in an auxiliary manner, and the maintenance efficiency of workers is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial sensors, and in particular to a method and system for collaborative analysis of multi-sensor fusion data for industrial situation awareness. Background Art

[0002] Sensors are an indispensable and important component in industry. They are responsible for collecting various physical quantity information of the environment or equipment and converting them into electrical signals for data processing and analysis. There are many types of sensors, including temperature sensors, pressure sensors, humidity sensors, flow sensors, and light sensors. Each sensor is designed for a specific application field. For example, temperature sensors are widely used in HVAC systems, food processing, and automation control to ensure accurate temperature monitoring and regulation; pressure sensors are used for safety monitoring and process control in the oil, gas, and chemical industries. In industrial automation, sensors can provide real-time feedback by continuously monitoring the operating status of equipment. Sensors are also often used to determine the status of equipment.

[0003] In industry, a single sensor is often used to detect the data of the target device. However, when a single sensor is working, faults may occur, such as data sampling being a fixed value, a value of 0, an error value, etc. At this time, staff are required to manually determine whether it is a device failure that causes the sensor sampling to be abnormal, or whether it is a sensor failure itself.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The purpose of the present invention is to provide an industrial situation awareness multi-sensor fusion data collaborative analysis method and system to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions: A method for collaborative analysis of multi-sensor fusion data for industrial situation awareness, the specific steps of which include: S1. Multiple sensors are set on the equipment. When the equipment is working stably, the working data is collected through the sensors, the working data dimension is unified, the working data is standardized, and standard data is generated; S2. Process the standard data, set a collection window, perform correlation analysis on the standard data within the collection window, and generate a window variance, where the window variance is used to reflect the variance of the standard data within the set collection window; S3, performing correlation analysis on the window variance to generate sensor abnormal points; S4. When the equipment is working normally, the working data collected by all sensors are compared and analyzed in pairs to generate sensor correlation coefficients; S5, setting one of the sensors as sensor A, setting the sensor with the highest correlation coefficient between the sensor and sensor A as sensor B, performing correlation analysis on the abnormal points of sensor A and the sampling points collected by sensor B, and generating a fault category determination index; S6. The fault category determination index and threshold Perform comparison and output the fault judgment category.

[0007] Furthermore, the sensor includes a temperature sensor, a pressure sensor, and a humidity sensor, and the working data It is used to reflect the data collected by the kth sensor when the sampling point is i, where i is used to index the sampling point and k is used to index the sensor. The value range of k is a positive integer from 1 to n, and the value range of i is a positive integer from 1 to s. The collection frequency of all sensors is set to the same and the sampling points are synchronized.

[0008] Furthermore, the working data dimensions are unified, and the working data collected by s sensors are All are standardized to generate standard data , the formula based on is: ; Standard data For work data The data obtained after standardization is Used to intuitively reflect the degree of fluctuation of data obtained by the sensor.

[0009] Furthermore, the acquisition window size is set to t sampling points, and the standard data is collected within the acquisition window t. Perform correlation analysis to generate window variance , the formula based on is: ; The sampling window is used to intercept the standard data of the kth sensor. The intercepted fragment is continuous and the intercepted size range is t sampling points. The acquisition window is numbered, j is used to index the number, and the window variance is It is used to reflect the variance of the standard data of the jth acquisition window. It is used to reflect the mean value of the standard data in the jth acquisition window, where the subscript k is used to index the sensor.

[0010] Furthermore, the window variance Perform correlation analysis to generate sensor anomaly points , the abnormal formula based on is: ; when When , it means that the standard data collected in the jth collection window of the kth sensor has a sudden change, which is an abnormal point and marked as a device failure or a sensor failure.

[0011] Furthermore, when the device is working normally, the working data collected by all sensors are compared and analyzed in pairs to generate a sensor correlation coefficient, which is used to reflect the correlation between sensors, and the formula based on it is: ; in, is the data of the qth sampling point of one of the sensors, is the average value of the data sampled by the sensor, is the data of the qth sampling point of another sensor, is the average value of the data sampled by the sensor, is the correlation coefficient between the two selected sensors. The closer it is to 1, the higher the correlation is.

[0012] Furthermore, the sensor with the abnormal point is set as sensor A, and the sensor correlation coefficient between it and The corresponding sensor with the maximum value is set as sensor B, and the correlation analysis is performed on the standard data collected by sensors A and B to generate the fault category judgment index GP; among which, the abnormal point of sensor A is: , the corresponding sampling points collected by sensor B are: , perform correlation analysis on the abnormal points of sensor A and the corresponding sampling points collected by sensor B, and generate the fault category judgment index GP, based on the formula: ; The fault category judgment index GP is used to judge the fault judgment of the A sensor.

[0013] Furthermore, the threshold Set to 0.9r-1.1r, when When the output fault judgment category is that the equipment is faulty, the equipment needs to be repaired. Not at threshold When it is within the range, the output fault judgment category is that sensor A is faulty, and sensor A needs to be repaired.

[0014] The present invention also provides an industrial situation awareness multi-sensor fusion data collaborative analysis system, which is used to execute an industrial situation awareness multi-sensor fusion data collaborative analysis method, including: The sensor collaboration system is used to set up multiple sensors on the equipment. When the equipment is working stably, the sensors collect working data, unify the working data dimensions, standardize the working data, and generate standard data. A data processing system is used to process the standard data, set a collection window, perform correlation analysis on the standard data within the collection window, and generate a window variance, wherein the window variance is used to reflect the variance of the standard data within the set collection window; Window analysis system, used to perform correlation analysis on window variance and generate sensor anomaly points; The correlation coefficient analysis system is used to compare and analyze the working data collected by all sensors in pairs when the equipment is working normally, and generate the sensor correlation coefficient; A fault category determination index module is used to set one of the sensors as sensor A, and set the sensor with the highest sensor correlation coefficient as sensor B, perform correlation analysis on the abnormal points of sensor A and the sampling points collected by sensor B, and generate a fault category determination index; Fault category output module, used to compare fault category judgment index with threshold Perform comparison and output the fault judgment category.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention performs correlation analysis on the data collected by sensors on the equipment. The sensors work together to collect sensor data, analyze the correlation between each sensor, and perform longitudinal analysis on the data collected by the sensors at the same sampling points and collection windows based on the correlation. A fault category determination index is generated to determine the source of the fault, thereby assisting in determining whether the fault is in the equipment or the sensor, greatly improving the maintenance efficiency of the staff. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the overall method flow of the present invention; Figure 2 It is a schematic diagram of the overall system flow of the present invention. DETAILED DESCRIPTION

[0017] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0018] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0019] Example: See also Figure 1 , the present invention provides a technical solution: A method for collaborative analysis of multi-sensor fusion data for industrial situation awareness. In industry, a single sensor is often used to detect the data of a target device. However, a single sensor may fail when working, such as data sampling of a fixed value, a 0 value, an error value, etc. At this time, a worker needs to manually determine whether the sensor sampling is abnormal due to a device failure or the sensor itself fails. The present invention uses other sensors to work together, collects sensor data, and analyzes the correlation between each sensor. Sensors with high correlation are used to associate abnormal sensors, thereby assisting in determining whether the device fails or the sensor fails, greatly improving the maintenance efficiency of the worker. The specific steps include: Step 1: Set up multiple sensors on the equipment. When the equipment is working stably, collect working data through the sensors, unify the working data dimensions, standardize the working data, and generate standard data; The sensors include temperature sensors, pressure sensors, humidity sensors, and may also be related sensors for detecting other data. The sampling frequencies of the sensors are set to the same value. At a specific sampling point, all sensors will collect data at the same time. The working data It is used to reflect the data collected by the kth sensor when the sampling point is i, where i is used to index the sampling point, k is used to index the sensor, the value range of k is a positive integer from 1 to n, and the value range of i is a positive integer from 1 to s.

[0020] In order to facilitate the common processing of all data, it is necessary to unify the working data dimension and reduce its value in proportion. All are standardized to generate standard data , the formula based on is: ; Standard data For work data After the data is standardized, is the variance of the data collected by the kth sensor, is the average value of the data collected by the kth sensor, the standard data Used to intuitively reflect the degree of fluctuation of data obtained by the sensor.

[0021] Step 2: In order to divide and process the standard data, a collection window is set, and correlation analysis is performed on the standard data within the collection window to generate a window variance, where the window variance is used to reflect the variance of the standard data within the set collection window; Set the acquisition window size to t sampling points, and perform standard data acquisition within the acquisition window t. Perform correlation analysis to generate window variance , the formula based on is: ; The sampling window is used to intercept the standard data of the kth sensor. The intercepted fragment is continuous and the intercepted size range is t sampling points. For example, is a sampling window, the acquisition window is numbered, j is used to index the number, and the window variance It is used to reflect the variance of the standard data of the jth acquisition window. It is used to reflect the mean of the standard data in the jth acquisition window, where the subscript k is used to index the sensor. The window variance is used to reflect the variance of the standard data in the set acquisition window, which can reflect the degree of change in the collected local data. The larger it is, the greater the degree of data variation.

[0022] Step 3: Perform correlation analysis on the window variance to generate sensor abnormal points; Window variance Perform correlation analysis to generate sensor anomaly points , the abnormal formula based on is: ; when When , it means that the standard data collected by the jth acquisition window of the kth sensor has a sudden change, which is an abnormal point, marking the sensor abnormal point , sensor abnormal point It is used to reflect the degree of variance change within two adjacent acquisition windows. The larger the value, the more unstable the data collected by the sensor, that is, the sensor fails or the device fails, and it is marked as a device failure or a sensor failure.

[0023] Step 4: When the equipment is working normally, the working data collected by all sensors are compared and analyzed in pairs to generate sensor correlation coefficients; When the device is working normally, the working data collected by all sensors are compared and analyzed in pairs to generate sensor correlation coefficients. The sensor correlation coefficients are used to reflect the correlation between sensors, and the formula is: ; in, is the data of the qth sampling point of one of the sensors, is the average value of the data sampled by the sensor, is the data of the qth sampling point of another sensor, is the average value of the data sampled by the sensor, is the correlation coefficient between the two selected sensors. The closer the value of r is to 1, the higher the correlation degree is, which means that the correlation degree between the data collected by the two selected sensors is higher.

[0024] Step 5: Set one of the sensors as sensor A, and set the sensor with the highest correlation coefficient as sensor B. Perform correlation analysis on the abnormal points of sensor A and the sampling points collected by sensor B to generate a fault category determination index. Compare and analyze the data of the sensor with abnormal data and the other sensor with the highest correlation to determine the source of the abnormal data. The sensor with the abnormal point is set as sensor A, and the correlation coefficient between it and the sensor The corresponding sensor with the maximum value is set as sensor B, and the correlation analysis is performed on the standard data collected by sensors A and B to generate the fault category judgment index GP; among which, the abnormal point of sensor A is: , the corresponding sampling points collected by sensor B are: , perform correlation analysis on the abnormal points of sensor A and the corresponding sampling points collected by sensor B, and generate the fault category judgment index GP, based on the formula: ; The fault category judgment index GP reflects the difference in window variance between the two sensors with the highest correlation at the same acquisition point, and is used to determine the fault judgment of sensor A. The farther the GP value is from 1, the greater the data difference between the two sensors, and the higher the probability of sensor failure. The closer the GP value is to 1, the higher the probability of equipment failure.

[0025] Step 6: Combine the fault category judgment index and threshold Perform comparison and output the fault judgment category.

[0026] Threshold Set to 0.9r-1.1r, when When the output fault judgment category is that the equipment is faulty, the equipment needs to be repaired. Not at threshold When it is within the range, the output fault judgment category is that sensor A is faulty, and sensor A needs to be repaired.

[0027] See also Figure 2 The present invention also provides an industrial situation awareness multi-sensor fusion data collaborative analysis system, which is used to execute an industrial situation awareness multi-sensor fusion data collaborative analysis method, including: The sensor collaboration system is used to set up multiple sensors on the equipment. When the equipment is working stably, the sensors collect working data, unify the working data dimensions, standardize the working data, and generate standard data. A data processing system is used to process the standard data, set a collection window, perform correlation analysis on the standard data within the collection window, and generate a window variance, wherein the window variance is used to reflect the variance of the standard data within the set collection window; Window analysis system, used to perform correlation analysis on window variance and generate sensor anomaly points; The correlation coefficient analysis system is used to compare and analyze the working data collected by all sensors in pairs when the equipment is working normally, and generate the sensor correlation coefficient; A fault category determination index module is used to set one of the sensors as sensor A, and set the sensor with the highest sensor correlation coefficient as sensor B, perform correlation analysis on the abnormal points of sensor A and the sampling points collected by sensor B, and generate a fault category determination index; Fault category output module, used to compare fault category judgment index with threshold Perform comparison and output the fault judgment category.

[0028] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0029] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0030] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0031] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A collaborative analysis method for multi-sensor fusion data for industrial situation awareness, characterized in that: The specific steps include: S1. Multiple sensors are set on the equipment. When the equipment is working stably, the working data is collected through the sensors, the working data dimension is unified, the working data is standardized, and standard data is generated; S2, processing the standard data, setting a collection window, performing correlation analysis on the standard data within the collection window, and generating a window variance, wherein the window variance is used to reflect the variance of the standard data within the set collection window; S3, performing correlation analysis on the window variance to generate sensor abnormal points; S4. When the equipment is working normally, the working data collected by all sensors are compared and analyzed in pairs to generate sensor correlation coefficients; S5, setting one of the sensors as sensor A, setting the sensor with the highest correlation coefficient between the sensor and sensor A as sensor B, performing correlation analysis on the abnormal points of sensor A and the sampling points collected by sensor B, and generating a fault category determination index; S6. Fault category determination index and threshold Perform comparison and output the fault judgment category.

2. The method for collaborative analysis of multi-sensor fusion data for industrial situation awareness according to claim 1 is characterized by: The sensors include temperature sensors, pressure sensors, and humidity sensors. It is used to reflect the data collected by the kth sensor when the sampling point is i, where i is used to index the sampling point and k is used to index the sensor. The value range of k is a positive integer from 1 to n, and the value range of i is a positive integer from 1 to s. The collection frequency of all sensors is set to the same and the sampling points are synchronized.

3. The method for collaborative analysis of multi-sensor fusion data for industrial situation awareness according to claim 2 is characterized by: Unify the working data dimension and collect the working data of s sensors All are standardized to generate standard data , the formula based on is: ； Standard data For work data The data obtained after standardization is Used to intuitively reflect the degree of fluctuation of data obtained by the sensor.

4. The method for collaborative analysis of multi-sensor fusion data for industrial situation awareness according to claim 3 is characterized by: Set the acquisition window size to t sampling points, and perform standard data acquisition within the acquisition window t. Perform correlation analysis to generate window variance , the formula based on is: ； The sampling window is used to intercept the standard data of the kth sensor. The intercepted fragment is continuous and the intercepted size range is t sampling points. The acquisition window is numbered, j is used to index the number, and the window variance is It is used to reflect the variance of the standard data of the jth acquisition window. It is used to reflect the mean value of the standard data in the jth acquisition window, where the subscript k is used to index the sensor.

5. The method for collaborative analysis of multi-sensor fusion data for industrial situation awareness according to claim 4 is characterized by: Window variance Perform correlation analysis to generate sensor anomaly points , the abnormal formula based on is: ； when When , it means that the standard data collected by the jth collection window of the kth sensor has a sudden change, which is an abnormal point and marked as a device failure or a sensor failure.

6. The method for collaborative analysis of multi-sensor fusion data for industrial situation awareness according to claim 5 is characterized by: When the device is working normally, the working data collected by all sensors are compared and analyzed in pairs to generate sensor correlation coefficients. The sensor correlation coefficients are used to reflect the correlation between sensors, and the formula is: ； in, is the data of the qth sampling point of one of the sensors, is the average value of the data sampled by the sensor, is the data of the qth sampling point of another sensor, is the average value of the data sampled by the sensor, is the correlation coefficient between the two selected sensors. The closer it is to 1, the higher the correlation is.

7. The method for collaborative analysis of multi-sensor fusion data for industrial situation awareness according to claim 6 is characterized by: The sensor with the abnormal point is set as sensor A, and the correlation coefficient between it and the sensor The corresponding sensor with the maximum value is set as sensor B, and the correlation analysis is performed on the standard data collected by sensors A and B to generate the fault category judgment index GP; among which, the abnormal point of sensor A is: , the corresponding sampling points collected by sensor B are: , perform correlation analysis on the abnormal points of sensor A and the corresponding sampling points collected by sensor B, and generate the fault category judgment index GP, based on the formula: ； The fault category judgment index GP is used to judge the fault judgment of the A sensor.

8. The method for collaborative analysis of multi-sensor fusion data for industrial situation awareness according to claim 7 is characterized by: Threshold Set to 0.9r-1.1r, when When the output fault judgment category is that the equipment is faulty, the equipment needs to be repaired. Not at threshold When it is within the range, the output fault judgment category is that sensor A is faulty, and sensor A needs to be repaired.

9. An industrial situation awareness multi-sensor fusion data collaborative analysis system, used to execute the industrial situation awareness multi-sensor fusion data collaborative analysis method according to claim 1, characterized in that: include: The sensor collaboration system is used to set up multiple sensors on the equipment. When the equipment is working stably, the sensors collect working data, unify the working data dimensions, standardize the working data, and generate standard data. A data processing system is used to process the standard data, set a collection window, perform correlation analysis on the standard data within the collection window, and generate a window variance, wherein the window variance is used to reflect the variance of the standard data within the set collection window; Window analysis system, used to perform correlation analysis on window variance and generate sensor anomaly points; The correlation coefficient analysis system is used to compare and analyze the working data collected by all sensors in pairs when the equipment is working normally, and generate the sensor correlation coefficient; A fault category determination index module is used to set one of the sensors as sensor A, and set the sensor with the highest sensor correlation coefficient as sensor B, perform correlation analysis on the abnormal points of sensor A and the sampling points collected by sensor B, and generate a fault category determination index; Fault category output module, used to compare fault category judgment index with threshold Perform comparison and output the fault judgment category.

Images